Lab4_ggplot_KCV

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

library(tidyverse)

## Warning in as.POSIXlt.POSIXct(Sys.time()): unknown timezone 'zone/tz/2019c.1.0/
## zoneinfo/America/New_York'

library(ggplot2)
library(RColorBrewer)
library(plotly)
library(DT)
library(dplyr)

SNPs <- read.table("23andMe_complete.txt", header = T, sep = "\t")

Excersice 1

ggplot(SNPs, aes(chromosome)) +
  geom_bar(colour="darkblue", fill="blue")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank())+
    ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs") +
    xlab("Chromosome")

#CHR sort
SNPs$chromosome = ordered(SNPs$chromosome, levels=c(seq(1, 22), "X", "Y", "MT"))

ggplot(SNPs, aes(chromosome)) +
  geom_bar(colour="darkblue", fill="blue")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank())+
  ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs") +
    xlab("Chromosome")

Excersice 2

CBP <- c("AA"="#999999","A"="#E69F00","AC"="#56B4E9","AG"="#009E73","AT"="#F0E442","C"="#0072B2","CC"="#D55E00","CG"="#CC79A7","CT"="#000000","D"="#FFCC00","DD"="#FF9900","DI"="#FF3300","G"="#99CC00","GG"="#33FF00","GT"="#00FFCC","I"="#9900FF","II"="#666699","T"="#CCFFCC","TT"="#996699","--"="#00CCFF")
ggplot(SNPs, aes(chromosome, fill=genotype)) +
  geom_bar(color="white")+
  scale_fill_manual(values = CBP)+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank())+
  ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs") +
    xlab("Chromosome")

Excersice 3

ppi <- 400
png("SNP_plot.png", width=6*ppi, height=6*ppi, res=ppi)

ggplot(SNPs, aes(chromosome, fill=genotype)) +
  geom_bar(color="black", position="dodge")+
  scale_fill_manual(values = CBP, name="Genotype")+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank())+
  ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs") +
    xlab("Chromosome")
dev.off()

## quartz_off_screen 
##                 2

Genotype counts per chromosome

Excersice 4

ggplot(SNPs, aes(genotype, fill=genotype)) +
  geom_bar(color="black", position="dodge")+
  scale_fill_manual(values = CBP, name="Genotype")+
 facet_wrap( ~ chromosome , ncol = 5)+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank(), axis.ticks = element_blank(), axis.text.x = element_blank(), axis.title.x = element_blank())+
  ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs")

#log2 trans
ggplot(SNPs, aes(genotype, fill=genotype)) +
  geom_bar(color="black", position="dodge")+
  scale_fill_manual(values = CBP, name="Genotype")+
 facet_wrap( ~ chromosome , ncol = 5)+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank(), axis.ticks = element_blank(), axis.text.x = element_blank(), axis.title.x = element_blank())+
  scale_y_continuous(trans = 'log2')+
  ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs")

Excersise 5

p <- ggplot(SNPs, aes(genotype, fill=genotype)) +
  geom_bar(color="black", position="dodge")+
  scale_fill_manual(values = CBP, name="Genotype")+
 facet_wrap( ~ chromosome , ncol = 5)+
  theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),panel.background = element_blank(), axis.ticks = element_blank(), axis.text.x = element_blank(), axis.title.x = element_blank())+
  scale_y_continuous(trans = 'log2')+
  ggtitle("Total SNPs for each genotype") +
    ylab("Total number of SNPs")

ggplotly(p)

Excersice 6

#library(dplyr)
SNP_Y <- filter(SNPs, chromosome == "Y")
datatable(SNP_Y)

## Warning in instance$preRenderHook(instance): It seems your data is too big
## for client-side DataTables. You may consider server-side processing: https://
## rstudio.github.io/DT/server.html